[Feat] New Provider - add langgraph

[ishaan-jaff]

[Feat] New Provider - add langgraph

This PR adds LangGraph as a new provider to LiteLLM, enabling users to call LangGraph agents via the standard OpenAI chat completions format. The implementation supports both streaming and non-streaming responses.

This PR adds LangGraph as a new provider to LiteLLM, enabling users to call LangGraph agents via the standard OpenAI chat completions format. The implementation supports both streaming and non-streaming responses.

Usage

Basic Completion

import litellm

response = litellm.completion(
    model="langgraph/agent",
    messages=[{"role": "user", "content": "What is 25 * 4?"}],
    api_base="http://localhost:2024",
)

print(response.choices[0].message.content)

Streaming

import litellm

response = litellm.completion(
    model="langgraph/agent",
    messages=[{"role": "user", "content": "What is the weather in Tokyo?"}],
    api_base="http://localhost:2024",
    stream=True,
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Proxy Configuration

model_list:
  - model_name: langgraph-agent
    litellm_params:
      model: langgraph/agent
      api_base: http://localhost:2024

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Error			Dec 10, 2025 8:28pm